Machine-led mood change
A machine is configured to identify a media file that, when played to a user, is likely to modify an emotional or physical state of the user to or towards a target emotional or physical state. The machine accesses play counts that quantify playbacks of media files for the user. The playbacks may be locally performed or detected by the machine from ambient sound. The machine accesses arousal scores of the media files and determines a distribution of the play counts over the arousal scores. The machine uses one or more relative maxima in the distribution in selecting a target arousal score for the user based on contextual data that describes an activity of the user. The machine selects one or more media files based on the target arousal score. The machine may then cause the selected media file to be played to the user.
1. A system comprising:
a biometric sensor to detect a biometric measurement of a user; and
a media selector machine including:
a play count accessor to access play counts that quantify playback of media files;
a media analyzer to:
access multi-dimensional user state scores of the media files; and
generate a distribution of the play counts over the multi-dimensional user state scores;
a target selector to:
determine a current multi-dimensional user state score of the user based on the biometric measurement of the user; and
select a target multi-dimensional user state score based on the current multi-dimensional user state score; and
a media selector to select a media file for playback to the user based on the distribution of the play counts and the target multi-dimensional user state score.
2. The system of claim 1 , wherein the media selector machine is incorporated into a vehicle.
3. The system of claim 2 , wherein the biometric sensor includes at least one of a heart rate sensor to detect a heart rate of the user or a facial sensor to detect a facial characteristic of the user.
4. The system of claim 2 , wherein the target selector is to select the target multi-dimensional user state score further based on contextual data associated with a user activity, and wherein the target selector is to identify the user activity based on measurements from one or more sensors in the vehicle.
5. The system of claim 4 , wherein the target selector identifies the user activity based on at least one of Global Positioning System (GPS) data, address book data, or calendar data.
6. The system of claim 4 , wherein the biometric sensor is one of the one or more sensors in the vehicle.
7. The system of claim 2 , further including a speaker in the vehicle to play the selected media file to the user.
8. A method comprising:
accessing, by executing an instruction with at least one processor, play counts that quantify playback of media files;
accessing, by executing an instruction with the at least one processor, multi-dimensional user state scores of the media files;
generating, by executing an instruction with the at least one processor, a distribution of the play counts over the multi-dimensional user state scores, the distribution associating play counts to corresponding multi-dimensional user state scores, the distribution including one or more relative maximum of play counts for one or more of the multi-dimensional user state scores;
determining, by executing an instruction with the at least one processor, a current multi-dimensional user state score of a user based on a biometric measurement of the user;
selecting, by executing an instruction with the at least one processor, a target multi-dimensional user state score based on the current multi-dimensional user state score;
identifying, by executing an instruction with the at least one processor, a first multi-dimensional user state score of a first relative maximum of the play counts based on the target multi-dimensional user state score; and
selecting, by executing an instruction with the at least one processor, a media file for playback to the user based on the first multi-dimensional user state score of the first relative maximum.
9. The method of claim 8 , wherein the current multi-dimensional user state score includes at least one of an arousal score, a valence score, or a dominance score.
10. The method of claim 8 , wherein the selecting the target multi-dimensional user state score is further based on input from the user.
11. The method of claim 8 , wherein the selecting of the media file includes:
determining that a candidate media file among the media files has a multi-dimensional user state score within a threshold tolerance of the first multi-dimensional user state score; and
selecting the candidate media file for playback to the user.
12. The method of claim 11 , wherein the selecting of the media file further includes:
determining a number of prior playbacks of the candidate media file to the user; and
selecting the candidate media file for playback to the user if the number of prior playbacks satisfies a threshold.
13. The method of claim 8 , wherein the selecting of the media file includes:
determining that a candidate media file among the media files has a multi-dimensional user state score outside of a threshold tolerance of the first multi-dimensional user state score; and
selecting the candidate media file for playback to the user.
14. The method of claim 13 , wherein the selecting of the media file includes:
determining a number of prior playbacks of the candidate media file to the user; and
selecting the candidate media file for playback to the user if the number of prior playbacks satisfies a threshold.
15. The method of claim 8 , wherein the identifying of the first multi-dimensional user state score of the first relative maximum of the play counts includes identifying a candidate relative maximum of a plurality of relative maxima as having a multi-dimensional user state score closest to the target multi-dimensional user state score.
16. The method of claim 15 , wherein the identifying of the first multi-dimensional user state score is further based on identifying the candidate relative maximum as having a multi-dimensional user state score between the current multi-dimensional user state score and the target multi-dimensional user state score.
17. A non-transitory machine readable storage medium comprising instructions that, when executed, cause at least one machine to at least:
determine a current multi-dimensional user state score for a user riding in a vehicle;
select a target multi-dimensional user state score based on contextual data associated with a user activity and the current multi-dimensional user state score;
access a plurality of media files, multi-dimensional user state scores associated with the plurality of media files, and a distribution of play counts over the multi-dimensional user state scores; and
select a media file for playback to the user based on the target multi-dimensional user state score and the distribution of play counts.
18. The non-transitory machine readable storage medium of claim 17 , wherein the instructions, when executed, further cause the at least one machine to play the selected media file to the user via a speaker in a vehicle.
19. The non-transitory machine readable storage medium of claim 17 , wherein the target multi-dimensional user state score is selected from a plurality of target multi-dimensional user state scores mapped to predetermined activities.
20. The non-transitory machine readable storage medium of claim 17 , wherein the instructions, when executed, further cause the at least one machine to identify the user activity based on at least one of location data, time of day, prior habits, or calendar entries.